Model reference · open weights
nomic-embed-text-moe-unsupervised is an open-weight embedding model from nomic-ai. nomic-embed-text-v2-moe-unsupervised (FP32) weighs 951 MB; the smallest configuration that runs it is RTX 3060 12 GB.
Summary of the nomic-ai/nomic-embed-text-v2-moe-unsupervised model card, 2026-10-01
What it is
| Released by | nomic-ai |
|---|---|
| Released | 2025-02-11 |
| Parameters | 475M |
| VRAM | 951 MB for the weights |
What it runs on
| Card | Runs | Memory |
|---|---|---|
| RTX 3060 12 GB | fits | 11.6 GB |
| RTX 4060 Ti 16 GB | fits | 15.4 GB |
| RTX 3090 24 GB | fits | 23.4 GB |
| RTX 4090 24 GB | fits | 23.4 GB |
| RTX 5090 32 GB | fits | 31.0 GB |
| L40S 48 GB | fits | 44.0 GB |
| A100 80 GB | fits | 78.2 GB |
| H100 80 GB | fits | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | fits | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | fits | 107 GB |
| H200 141 GB | fits | 138 GB |
| B200 180 GB | fits | 176 GB |
From the model card
nomic-embed-text-v2-moe-unsupervised is multilingual MoE Text Embedding model. This is a checkpoint after contrastive pretraining from multi-stage contrastive training of the
final model.
If you want to use a model to extract embeddings, we suggest using nomic-embed-text-v2-moe
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.